Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    model performance

    np_max-act · gemini-2.0-flash

    This neuron activates on words and phrases that talk about improving or measuring performance (e.g., “improve,” “performance,” “improving”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    áno
    -0.06
     Thumbnail
    -0.06
     zkou
    -0.06
    anlık
    -0.06
     salad
    -0.06
     estudio
    -0.05
     simulator
    -0.05
     giảng
    -0.05
    unar
    -0.05
    CDF
    -0.05
    POSITIVE LOGITS
     ''),
    0.09
    ceil
    0.07
    ={},
    0.07
     声
    0.07
     microseconds
    0.07
     alg
    0.07
     competing
    0.07
    Proceed
    0.07
    (hero
    0.06
     Raises
    0.06
    Act Density 0.033%

    No Known Activations